Seminar & Colloquium
[세미나: 4월 6일(수), 오전 9시 30분] Florida State University, 박치우 교수
TITLE
Machine Learning for Materials Research
SPEAKER
박치우 교수, Department of Industrial and Manufacturing Engineering, Florida State University
EDUCATION
-2001 Seoul National University, Industrial Engineering (Cum Laude), B.S.
-2011 Texas A&M University, Industrial & Systems Engineering, Ph.D.
PROFESSIONAL EXPERIENCES
-2017~present Associate Professor (with tenure), Florida State University. Industrial and Manufacturing Engineering
-2020~2020 Visiting Professor, Sungkyunkwan University. Systems Management Engineering. e-Manufacturing Lab
-2019~2019 Visiting Professor, Air Force Research Lab. Manufacturing and Materials Directorate
-2011~2017 Assistant Professor, Florida State University. Industrial and Manufacturing Engineering
-2005~2006 Consultant, Deloitte Consulting. IT Consulting Service.
-2001~2005 Software Engineer, Handysoft Corp. Real-time Enterprise Research Center.
| Date | Wednesday, April 6th, 2022
| Time | 09:30 ~
| Venue | 온라인 강의 (https://snu-ac-kr.zoom.us/j/94146537979, 회의 ID: 941 4653 7979 )
[Abstract]
This talk introduces the presenter’s past 15-year work in the intersection of data science and materials science, with two primary focuses: materials imaging and autonomous research experimentation. Advancements in temporal and spatial resolutions of microscopes promise to expand the frontiers of our understanding of materials science. Imaging techniques produce images at a high frame rate, streaming out massive object data concerning sizes, shapes, motions, interactions and other attributes of complex material objects. Manual analysis of object data is inefficient and may no longer be feasible given the complexity and volume of the data. The first half of this talk overviews our past developments in object data analysis and their applications for understanding the relationship between structures and properties of objects in materials and biological science. The other half of this talk focuses on machine learning modeling for autonomous research experimentation. Most materials research is conducted through chemical or computer experiments, iterating multiple stages of planning, experiment, and analysis steps. Human-driven experimental design has been successful for a small-scale experimental campaign involving three or fewer design factors. Planning bigger-scale experimental campaigns is well beyond the regime of human efficiency. Inefficient experimental planning has been the main reason for many unnecessary experimental iterations, slowing down the pace of scientific discovery significantly. Emerging trends in materials research are to use robotic operators and machine learning algorithms to achieve the AI-driven optimization of experimental planning, namely, autonomous experimentation. The second half of this talk introduces our recent developments for the autonomous system.
Bio of the Speaker. Dr. Chiwoo Park received B.S. in industrial engineering at Seoul National University and a Ph.D. degree in industrial engineering at Texas A&M University in 2011. He is currently an Associate Professor in the Department of Industrial and Manufacturing Engineering at Florida State University and a principal investigator at High-Performance Material Institute. His main research interest lies in machine learning and data science, focusing on modeling and analyzing object data such as image, shape, motion, function, and directional data. His other research is AI-driven scientific discovery, focusing on modeling physical and computer experiments and sequential decision-making for effective exploration of large dimensional experimental spaces. He authored more than 50 journal publications, many on top machine learning journals. He recently authored a book ‘Data Science for Nano Image Analysis.’ He received numerous awards, including the best student paper award at IEEE Conferences on Automation Science and Engineering in 2008, the Ralph E. Powe Junior Faculty Award from the Oak Ridge Associated Universities in 2013, the IIE Best Application Paper Award in 2014, Brainpool Fellowship in 2020, AFRL Summer Faculty Fellowships in 2021 & 2022, Editor’s Choice for Featured Article, IISE Transactions 2022. He is Associate Editor of IISE Transactions and IEEE Transactions on Automation Science and Engineering. He is a senior member of IISE and IEEE, and he is also a member of INFORMS and MSA.
| Host | Prof. Jin Young Kim (880-8315)